mlsanityData to 14 Oct 2026

Vroom-Vroom at SHROOM-Visions: A Multi-Judge Committee for Detecting Hallucinated Spans in Vision-Language Outputs

arXiv 2609.17327 ↗First posted 15 Sep 2026cs.CL cs.AIcited by 0

On the map: Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs

Abstract (arXiv)

This paper describes our submission to the SHROOM-Visions shared task on detecting and classifying hallucinated character spans in vision-language model outputs across four languages. We employ several fine-tuned vision-language models as independent annotators and combine their span predictions through character-level majority voting, and additionally explore activation probes. The approach ranks first in three of four languages and places on the podium in every language and metric. Our analysis indicates that disagreement among diverse models tracks disagreement among human annotators.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 16 of its 31 references that are in the map. First posted on arXiv 15 Sep 2026.

Builds on

16 of 31 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination7 Aug
  2. 2025HalluShift++: Bridging Language and Vision through Internal Representation Shifts for Hierarchical Hallucinations in MLLMs8 Dec
  3. 2024VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation18 Nov

Other references · 13

  1. 2024INSIDE: LLMs' Internal States Retain the Power of Hallucination Detectioncited by 323
  2. 2024Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMscited by 259
  3. 2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 256
  4. 2017FOIL it! Find One mismatch between Image and Language captioncited by 95
  5. 2023SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistencycited by 90
  6. 2025Detecting High-Stakes Interactions with Activation Probescited by 53
  7. 2025Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViTcited by 17
  8. 2024Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Ambiguous Prompts and Unanswerable Questionscited by 9
  9. 2025Revisiting LLM Value Probing Strategies: Are They Robust and Expressive?cited by 8
  10. 2024Enhancing Hallucination Detection through Perturbation-Based Synthetic Data Generation in System Responsescited by 5
  11. 2026Can Humans Dream of Electric Sheep? Human-Written Samples for Fine-Grained Vision-and-Language Hallucination Benchmarkingcited by 4
  12. 2024Controlled Automatic Task-Specific Synthetic Data Generation for Hallucination Detectioncited by 3
1 more
  1. 2026What are They Thinking? Delineation, Probing, and Tracking of Concepts in LLMscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026SpanCalib-VLM: Calibrated Hallucination Span Detection in Vision-Language Models
  2. 2026Hallucination Span Detection with Input-Side Evidence Alignment
  3. 2024Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs
  4. 2026Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations
  5. 2024Mitigating Multilingual Hallucination in Large Vision-Language Models
  6. 2026LLM-as-Judge Framework for Evaluating Tone-Induced Hallucination in Vision-Language Models
  7. 2026Beyond Document Grounding: Span-Level Hallucination Detection over Code, Tool Output, and Documents
  8. 2025HalluSearch at SemEval-2025 Task 3: A Search-Enhanced RAG Pipeline for Hallucination Detection